confluence MCP Server

README

Confluence Communication Server MCP Server

Interact with Confluence

This is a TypeScript-based MCP server that provides tools to interact with Confluence. It demonstrates core MCP concepts by providing:

Tools for executing CQL queries to search pages
Tools for retrieving the content of Confluence pages

Confluence Communication Server MCP server

Features

Confluence Tools

`execute_cql_search`

Purpose: Run a CQL query to search for Confluence pages.
Parameters: cql, limit (default: 10).

`get_page_content`

Purpose: Fetch the content of a Confluence page.
Parameters: pageId.

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

Installing via Smithery

To install Confluence Communication Server MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @KS-GEN-AI/confluence-mcp-server --client claude

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "Confluence communication server": {
      "command": "node",
      "args": [
        "/PATH_TO_THE_PROJECT/build/index.js"
      ],
      "env": {
        "CONFLUENCE_URL": "https://XXXXXXXX.atlassian.net/wiki",
        "CONFLUENCE_API_MAIL": "Your email",
        "CONFLUENCE_API_KEY": "KEY_FROM: https://id.atlassian.com/manage-profile/security/api-tokens"
      }
    }
  }
}

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

confluence-mcp-server FAQ

How do I install the confluence-mcp-server?

Install dependencies using 'npm install' and follow the build instructions in the repository README.

What parameters are required to execute a CQL search?

You need to provide a 'cql' query string and optionally a 'limit' for the number of results (default is 10).

How can I fetch the content of a Confluence page?

Use the 'get_page_content' tool with the 'pageId' parameter specifying the target page.

Is the confluence-mcp-server compatible with multiple LLM providers?

Yes, it works with OpenAI, Anthropic Claude, and Google Gemini by exposing Confluence data via MCP.

Can I customize the number of search results returned?

Yes, the 'limit' parameter in the 'execute_cql_search' tool controls the maximum number of pages returned.

What programming language is the confluence-mcp-server written in?

It is implemented in TypeScript for robust MCP server development.

Does the server support real-time updates from Confluence?

The current implementation focuses on query and retrieval; real-time updates would require additional integration.

How secure is the confluence-mcp-server when accessing Confluence data?

Security depends on your Confluence API credentials and MCP's scoped, secure interaction principles.

confluence-mcp-server

Use This MCP server To